Segmentation fault

[Yshuo-Li]

python runner.py \
        --gpu 0\
        --phase 'test'\
        --weights './ckpt/IGNN_x4.pth'\
        --scale 4\
        --demopath [my_path]\
        --testname 'Demo'

By running the command, I got:

...
Using GPUs NUMBER: 1
[INFO] 2021-03-14 16:35:38.938372 Complete collecting files for TEST. Total test images: 100.
[DEBUG] 2021-03-14 16:35:41.253575 Parameters in IGNN: 49512553.
[INFO] 2021-03-14 16:35:44.150203 Recovering from ./ckpt/IGNN_x4.pth ...
[INFO] 2021-03-14 16:35:44.262738 Recover complete. Current Epoch #0, Best_PSNR = 0 at Epoch #0.
srun: error: SH-IDC2-172-20-21-49: task 0: Segmentation fault (core dumped)

Why Segmentation fault?
I found that this error is related to memory, it may be related to the acceleration of CUDA. Could I run the model on Pytorch only?